Introduction Intracranial aneurysms have a high prevalence in human population. It also has a heavy burden of disease and high mortality rate in the case of rupture. Convolutional neural network(CNN) is a type of deep learning architecture which has been proven powerful to detect intracranial aneurysms. Methods Four databases were searched using artificial intelligence, intracranial aneurysms, and synonyms to find eligible studies. Articles which had applied CNN for detection of intracranial aneurisms were included in this review. Sensitivity and specificity of the models and human readers regarding modality, size, and location of aneurysms were sought to be extracted. Random model was the preferred model for analyses using CMA 2 to determine pooled sensitivity and specificity. Results Overall, 20 studies were used in this review. Deep learning models could detect intracranial aneurysms with a sensitivity of 90/6% (CI: 87/2–93/2%) and specificity of 94/6% (CI: 0/914–0/966). CTA was the most sensitive modality (92.0%(CI:85/2–95/8%)). Overall sensitivity of the models for aneurysms more than 3 mm was above 98% (98%-100%) and 74.6 for aneurysms less than 3 mm. With the aid of AI, the clinicians’ sensitivity increased to 12/8% and interrater agreement to 0/193. Conclusion CNN models had an acceptable sensitivity for detection of intracranial aneurysms, surpassing human readers in some fields. The logical approach for application of deep learning models would be its use as a highly capable assistant. In essence, deep learning models are a groundbreaking technology that can assist clinicians and allow them to diagnose intracranial aneurysms more accurately.
Objective In this systematic review and meta-analysis, we investigated the efficacy and safety of middle meningeal artery embolization (MMAE) using particle embolic agents to treat cSDH. Methods To retrieve articles investigating outcomes of patients following MMAE with particle agents and to compare their outcome with conventional treatment, Scopus, PubMed, Embase, and Web of Science were searched using relevant keywords. Original articles with more than 10 cases were included. The meta-analysis was carried out using the R studio and the random-effects model. Publication bias was assessed using Peter's test and quality assessment using NIH tools. Results Eleven studies with 359 patients were included. The analysis revealed a pooled recurrence rate of 5% (CI: 3–8%), a need for reoperation rate of 5% (3–9%), and a peri-procedural complication rate of 4% (CI:2–9%) following MMAE with particle embolic agents. The pooled rates of decrease in size or resolution of the hematoma were 85% (CI:66–94%) and 66% (39–86%), respectively. Comparing MMAE using particulate embolysate with conventional treatments, risk ratio (RR) of 0.10 (CI:0.04–0.27) was achieved for recurrence, 0.25(CI:0.13–0.49) for reoperation, and 0.34 (CI:0.16–0.27) for peri-procedural complications. 91% of cSDH cases responded to MMAE with particles in the way they showed either down-sizing or complete resolution of the hematoma on follow-up imaging. In comparison, this rate was found to be 63% following conventional treatment. Conclusion Middle meningeal artery embolization using particle embolysates is a safe and effective technique for the treatment of cSDH, whether as a standalone intervention or in combination with conventional treatments.
BackgroundThis study aimed to investigate the application of deep learning (DL) models for the detection of subdural hematoma (SDH).MethodsWe conducted a comprehensive search using relevant keywords. Articles extracted were original studies in which sensitivity and/or specificity were reported. Two different approaches of frequentist and Bayesian inference were applied. For quality and risk of bias assessment we used Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2).ResultsWe analyzed 22 articles that included 1,997,749 patients. In the first step, the frequentist method showed a pooled sensitivity of 88.8% (95% confidence interval (CI): 83.9% to 92.4%) and a specificity of 97.2% (95% CI 94.6% to 98.6%). In the second step, using Bayesian methods including 11 studies that reported sensitivity and specificity, a sensitivity rate of 86.8% (95% CI: 77.6% to 92.9%) at a specificity level of 86.9% (95% CI: 60.9% to 97.2%) was achieved. The risk of bias assessment was not remarkable using QUADAS-2.ConclusionDL models might be an appropriate tool for detecting SDHs with a reasonably high sensitivity and specificity.
Introduction: Coronary artery bypass grafting is of the most major surgeries performed around the world. Even though advances are achieved in the surgical technique, a relatively high complication rate regarding circulation is still observed. These complications are believed to be related to cardiopulmonary bypass flow types, pulsatile and nonpulsatile. With renal complications being one of the most important ones, we aim to evaluate the effect of choice of these two flow types on patients' renal function in a randomized controlled trial. Method: The study is a double blind randomized clinical trial. Patients with left ventricular dysfunction who were candidates for CABG and were between the ages of 40 to 75 were included in this study. The patients then were randomly assigned into two groups of intraoperative pulsatile and nonpulsatile flow type. The patients renal function markers such as 24-hour urine output, blood urea nitrogen and serum creatinine levels and creatinine clearance were evaluated before and CABG and afterwards in the ICU ward. The results were then analyzed using SPSS 23 software. Results: of the initial 80 patients enrolled in this study, 16 patients were dropped due to unwillingness to continue follow-up and limitation of data gathering. Patients demographic data between two groups did not differ significantly. No statistically significant difference was observed between the 24 patients undergoing surgery with pulsatile flow and 40 with nonpulsatile flow regarding renal function. Both groups had a decrease in creatinine clearance during their ICU stay. Patients in the pulsatile flow group had less intubation time, less need for blood transfusion but more bleeding after the surgery. Conclusion: Our study indicated that there is no difference between the use of pulsatile versus nonpulsatile flow regarding patients' renal outcome. Our participants had a relatively broader age range than similar studies, including younger patients. This plus having an acceptable number of patients evaluated may illustrate that the differences in these two flow types may be dependent on other risk factors depending on the studied population. Further investigations with focal groups could lead us towards a better understanding how these two flow types differ.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.